lightclaw

# LightClaw

LightClaw is a **self-hosted Telegram AI agent** inspired by OpenClaw: a small Python codebase with long-term memory, multi-provider LLM routing, skills, and local multi-agent delegation.

If you are searching for an **OpenClaw alternative**, **OpenClaw in Python**, or a **Telegram AI bot with memory**, this project is built for that workflow.

<div align="center">
  <img src="logo.png" alt="LightClaw logo" width="420">
</div>

## Security Disclaimer

LightClaw can execute impactful actions (file edits and delegated local agent runs).  
Use least-privilege credentials, review installed skills, and restrict bot access with `TELEGRAM_ALLOWED_USERS`.

## Why LightClaw

- Lightweight and forkable: understand the core quickly and customize without framework overhead.
- Practical for solo builders: run on small VPS machines with minimal setup.
- Built for real usage: memory recall, file operations, skills, and delegated coding agents.

## Core Features

- Infinite memory with SQLite + semantic recall.
- 6 LLM providers: OpenAI, xAI, Anthropic, DeepSeek, DeepSeek, Z-AI.
- Telegram-first experience with command-driven workflow.
- Local terminal chat mode (`lightclaw chat`) using the same runtime stack.
- Skills system (hub + local skills).
- Local agent delegation (`codex`, `deepseek`) for large coding tasks.
- Smart multi-agent orchestration with auto-planning, dependencies, and confirmation flow.
- Workspace-native code generation/editing with compact delta reports.
- Optional voice transcription with Groq Whisper.

## Quick Start

### 1) One-command setup (recommended)

```bash
git clone https://github.com/OthmaneBlial/lightclaw.git && cd lightclaw && bash setup.sh
```

`setup.sh` does everything automatically:

- Installs the `lightclaw` command at `~/.local/bin/lightclaw`
- Writes your config to `~/.env`
- Creates runtime files in `~/.lightclaw`

Then run:

```bash
lightclaw run
```

If your shell has not reloaded `PATH` yet, use:

```bash
~/.local/bin/lightcl